Search Results for author: Kyle Luh

Found 2 papers, 0 papers with code

Robustness Implies Generalization via Data-Dependent Generalization Bounds

no code implementations27 Jun 2022 Kenji Kawaguchi, Zhun Deng, Kyle Luh, Jiaoyang Huang

This paper proves that robustness implies generalization via data-dependent generalization bounds.

Generalization Bounds

A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates

no code implementations13 Aug 2019 Zhixian Lei, Kyle Luh, Prayaag Venkat, Fred Zhang

The goal is to design an efficient estimator that attains the optimal sub-gaussian error bound, only assuming that the random vector has bounded mean and covariance.

Computational Efficiency LEMMA

Cannot find the paper you are looking for? You can Submit a new open access paper.